IbrahimSalah commited on
Commit
e3a3bc4
1 Parent(s): b03ec7d

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 46,
3
+ "<s>": 45
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": "[PAD]",
27
+ "unk_token": "[UNK]"
28
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "39": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "40": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "45": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "46": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [
37
+ "<s>",
38
+ "</s>"
39
+ ],
40
+ "bos_token": "<s>",
41
+ "clean_up_tokenization_spaces": true,
42
+ "do_lower_case": false,
43
+ "eos_token": "<s>",
44
+ "model_max_length": 1000000000000000019884624838656,
45
+ "pad_token": "[PAD]",
46
+ "processor_class": "Wav2Vec2ProcessorWithLM",
47
+ "replace_word_delimiter_char": " ",
48
+ "target_lang": null,
49
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
50
+ "unk_token": "[UNK]",
51
+ "word_delimiter_token": "|"
52
+ }
vocab.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ ".": 41,
3
+ "[PAD]": 40,
4
+ "[UNK]": 39,
5
+ "|": 36,
6
+ "ء": 19,
7
+ "آ": 18,
8
+ "أ": 42,
9
+ "إ": 43,
10
+ "ئ": 44,
11
+ "ا": 26,
12
+ "ب": 9,
13
+ "ة": 14,
14
+ "ت": 15,
15
+ "ث": 1,
16
+ "ج": 17,
17
+ "ح": 8,
18
+ "خ": 33,
19
+ "د": 12,
20
+ "ذ": 10,
21
+ "ر": 27,
22
+ "ز": 11,
23
+ "س": 0,
24
+ "ش": 6,
25
+ "ص": 37,
26
+ "ض": 31,
27
+ "ط": 32,
28
+ "ظ": 20,
29
+ "ع": 4,
30
+ "غ": 30,
31
+ "ف": 28,
32
+ "ق": 3,
33
+ "ك": 25,
34
+ "ل": 5,
35
+ "م": 38,
36
+ "ن": 7,
37
+ "ه": 29,
38
+ "و": 22,
39
+ "ى": 24,
40
+ "ي": 2,
41
+ "َ": 23,
42
+ "ُ": 16,
43
+ "ِ": 13,
44
+ "ّ": 34,
45
+ "ْ": 35,
46
+ "ھ": 21
47
+ }